dsh-plugin-rollout-scout
Detect which conversation model your DeepSeek Harness account is served: score probe conversations' live chain-of-thought, cancel old-model probes in seconds, keep confident catches.
28 results
Detect which conversation model your DeepSeek Harness account is served: score probe conversations' live chain-of-thought, cancel old-model probes in seconds, keep confident catches.
Plugin-combination analysis for the DeepSeek Harness: dependency trees, conflict detection, risk scoring with prediction, visualization, and combination simulation.
Long-task gatekeeper for DeepSeek Harness: detects one-shot mammoth requests, asks whether to plan first, and scaffolds plan.md + a capped goal before the agent starts
DeepSeek Harness task-protection plugin: plugin preflight scanner (catches missing `inject` declarations that crash the host), loop detection (repeated identical tool calls -> steer to a new approach), recursion guard (nested subagent depth cap), and interruption awareness (status route with safeToRestart). Never terminates tasks — only steers via injected messages. Zero npm dependencies.
DeepSeek Harness 创意指导 Agent 插件:6 维评估 + 自适应追问生成通用美学 brief(JSON,平台无关),AIGC 痕迹去除润色,框架逻辑抽成可测试工具(cd_assess / cd_detect_conflict / cd_polish_type / cd_save_brief)
Diary Detective for DeepSeek Harness — a warm mirror that reads journals, illuminates blind spots, and gives gentle daily feedback. 赛博日记侦探:一面有温度的镜子,读日记、照见盲点、给温柔反馈。
DeepSeek balance banner for DSH: top-right USD/CNY balance chips with damage/gain animations and peak/valley detection
Supervisor daemon for DSH Web resilience — auto-detect crashes, rollback to LKG, report
DSH plugin: structured test runner tool (test_run) — auto-detect vitest/jest/pytest/node:test, run tests, parse failure summaries for the model.
灰度模型检测工具:一键开测 40 个并发 dsh 会话(V4 Pro + max 思考),流式监听思维链——出现 I'm/I'll 特征标记为灰度神模型,出现 Let me 标记为正常模型;统计灰度出现率,结果可在设置页查看。
Real-time repetition guard for DeepSeek Harness (DSH): stops model generation when the same string repeats >=10 times in the streamed output. 实时检测 DSH 大模型流式输出中的重复内容,同一字符串重复十次以上立即停止生成。
Persian (Farsi) RTL fix for DeepSeek Harness: automatic per-paragraph direction and mixed-language detection (Persian text starting with English words), thinking cells, tool cells, user bubbles and question boxes.
Local repository intelligence for DeepSeek Harness: stack detection, dependency maps, and module-reference analysis 鈥?no extra services, everything runs on your filesystem.
DeepSeek Harness plugin: open the current workspace in a detected editor (VS Code, GoLand, PhpStorm, HBuilderX, …) from a header dropdown
DeepSeek Harness plugin: creates a Windows desktop shortcut that launches dsh web in a Chrome app-mode window (auto-detects Chrome, waits for the port, no duplicate windows).
DeepSeek Harness plugin conflict checker: pre-flight duplicate-id detection and optional real startup smoke test.
输入一张图像,对其中的人头人体进行检测,输出图片中所有目标的检测框、置信度和标签。
输入一张图像,对其中的电动自行车进行检测,输出图片中所有目标的检测框、置信度和标签。
输入一张图像,输出图像中所有识别到的野生动物的检测框、置信度及标签。
包括日常物体检测、昆虫识别、植物识别、动物识别、电动自行车检测、手机检测、手势检测、火焰检测、香烟检测、人头人体检测、野生动物检测、鸟类识别、宠物情绪识别、菜品识别、安全帽人体检测、行人检测、反光衣检测、车辆检测、图像分类、目标检测、旋转目标检测、人体姿态估计和万物识别。
检测图像中的80类COCO目标(人、车、动物、日常物品等),输出边界框、置信度和类别标签。
输入一张图像,对其中的手机进行检测,输出图片中所有目标的检测框、置信度和标签。
输入一张图像,对其中的手势进行检测,输出图片中所有目标的检测框、置信度和标签。
Result-aware stuck-loop guard for DeepSeek Harness: advisory nudges plus a monotonic hard stop. Only repeats with identical results count, so progressing polls and post-edit re-reads never trigger.